Description:TECHNICAL FIELD
[001] The present disclosure generally relates to the field of automated interview systems. In particular, the present disclosure relates to a system and a method for conducting interviews with real-time scoring using Artificial Intelligence (AI), thereby enhancing efficiency, improving accuracy, and reducing carbon emissions by optimizing data transfer, processing, and resource utilization.

BACKGROUND
[002] Traditional talent acquisition and interview management solutions are heavily reliant on human interviewers for both conducting interviews and evaluating the responses provided by candidates. Therefore, the existing interview process relies on human dependency and introduces a variety of challenges that can negatively impact the efficiency and effectiveness of the recruitment process. One of the primary challenges is the inconsistency in candidate evaluation, as human assessments are often influenced by subjective biases. For example, two interviewers assessing the same candidate may arrive at significantly different conclusions due to differences in personal judgment, mood, or prior experience. The subjectivity can result in unfair evaluations and missed opportunities to identify the most suitable candidates.
[003] Additionally, the requirement for human interviewers creates logistical hurdles. Coordinating schedules between candidates, interviewers, and other stakeholders can be time-consuming and often leads to delays, which becomes even more pronounced in large-scale recruitment drives or when dealing with candidates located in different time zones. The reliance on human availability can also lead to bottlenecks, particularly when the demand for interviews outpaces the capacity of available interviewers.
[004] Another limitation of human-driven processes is the significant amount of time and resources required to evaluate candidates. Each interview requires preparation, execution, and post-interview analysis, which can be labour-intensive and costly. Further, the existing interview process is inefficient when dealing with a high volume of candidates. Additionally, organizations may struggle to assess a large pool of applicants within a reasonable timeframe, potentially leading to lost opportunities or prolonged vacancies. Furthermore, traditional methods lack standardization. The variability in assessment criteria and evaluation techniques used by different interviewers can result in inconsistent outcomes. The candidates may receive different levels of scrutiny or face varying levels of difficulty, depending on the interviewer assigned to each candidate. The lack of uniformity can undermine the fairness and credibility of the recruitment process.
[005] The challenges associated with human interviewers are further exacerbated by the increasing demand for remote and virtual interviews. In such cases, the technical and logistical complexities of managing online interactions add a layer of difficulty. Issues such as unreliable network connections, difficulties in monitoring candidate behaviour, and challenges in ensuring secure and cheat-proof interview environments can hinder the effectiveness of traditional interview methods. Overall, the reliance on human interviewers to conduct and evaluate interviews introduces inefficiencies, inconsistencies, and limitations that can significantly impact the recruitment process. Accordingly, there is a growing need for an automated, technology-driven solution that can address at least these challenges by providing consistent, scalable, and objective assessments of candidates while minimizing resource requirements and logistical complications.
[006] Further, in existing online interview systems, carbon emissions occur due to utilization of Large Language Models (LLMs) and high data transfer and processing requirements associated with continuous live video streaming and extensive server utilization. The existing online interview systems often rely on prolonged, high-resolution video calls that demand significant bandwidth and computational resources, resulting in increased energy consumption by both end-user devices and centralized servers. The reliance on data centres, which consume substantial electricity for processing and cooling, further exacerbates the environmental impact. Additionally, inefficient scheduling or prolonged sessions can increase unnecessary resource usage, making the process less environmentally sustainable. Addressing the inefficiencies is crucial for reducing the carbon footprint of online interviews while maintaining functionality and reliability.
[007] Additionally, the existing technologies for conducting interviews often rely on repetitive question sets or answers sourced directly from the internet, limiting an ability to evaluate candidates effectively for unique job roles. The existing systems lack adaptability and fail to provide tailored assessments aligned with dynamic industry standards. Moreover, many existing solutions do not support real-time evaluation of voice-based or video-based responses, missing critical insights into communication skills of a candidate, such as tone, confidence, and emotion. Therefore, the absence of such capabilities compromises the depth and accuracy of candidate evaluations, making the process less robust and comprehensive.
[008] Further drawback of the existing arts is that candidate responses are often compared with answers found on the internet, which can lead to inaccuracies in the evaluation process. The internet-based evaluation method may not accurately assess true understanding or problem-solving abilities of the candidate, as responses sourced from the internet may be memorized or plagiarized rather than demonstrating original thought. Additionally, relying on internet-based answers can result in a limited evaluation scope, as candidates may not be tested on their ability to adapt or think critically in real-time scenarios, thereby compromising the overall effectiveness of the interview process.
[009] Therefore, there is a need to address at least the above-mentioned drawbacks and any other shortcomings, or at the very least, provide a valuable alternative to the existing methods and systems.

OBJECTS OF THE PRESENT DISCLOSURE
[010] An object of the present disclosure is to provide a system and a method for conducting automated interviews that utilize Artificial Intelligence (AI) to perform real-time scoring, enabling accurate and consistent evaluation of candidates without relying on human interviewers.
[011] Another object of the present disclosure is to provide a system and a method for enabling an authentication of applicants through advanced biometric verification, including facial recognition, voice recognition, and real-time monitoring, ensuring a secure and cheat-proof environment for online interviews.
[012] Yet another object of the present disclosure is to provide a system and a method for optimizing an interview process by presenting predefined questions based on job requirements, utilizing employer expertise, global knowledge, or generative AI models to create tailored assessments.
[013] Yet another object of the present disclosure is to provide a system and a method for minimizing carbon emissions during online interviews by employing AI-driven simulations of video calls that reduce data transfer, processing load, and energy consumption, as compared to traditional video conferencing systems.
[014] Yet another object of the present disclosure is to provide a system and a method for providing real-time reports to applicants and employers, offering insights into the performance of the applicants across verbal, non-verbal, and written communication, as well as behavioural and psychological indicators.
[015] Yet another object of the present disclosure is to provide a system and a method for conducting an interview through a wireless medium to establish a one-to-one communication between an applicant device associated with an applicant and the system without using intermediate systems, thereby reducing carbon emissions.

SUMMARY
[016] An aspect of the present disclosure relates to a method for conducting interviews with real-time scoring using Artificial Intelligence (AI) and reducing carbon emissions. The method includes receiving, by a system, profile data of each of a plurality of applicants. Further, the method includes selecting, by the system, an applicant from the plurality of applicants based on the received profile data and determining, by the system, identity information associated with the applicant based on the profile data and a token provided to the applicant, wherein the identity information comprises an image frame of the applicant, documents associated with the applicant, and biometric data of the applicant. Further, the method includes validating, by the system, the identity information and the profile data associated with the applicant. Further, upon validation, the method includes initiating, by the system, an interview through a wireless medium to establish a one-to-one communication between an applicant device and the system without using intermediate systems, wherein the interview is conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device to the applicant. Further, the method includes receiving, by the system, responses and answers with respect to the set of interview questions from the applicant device of the applicant during the interview and evaluating in real-time, by the system via an AI engine, one or more attributes associated with the responses and the answers received from the applicant by comparing the one or more attributes with preset answers corresponding to the set of interview questions. Further, the method includes generating, by the system, a score for each of the one or more attributes associated with the responses and the answers, and a report based on the generated score of the applicant and providing, by the system, the report of the applicant to a plurality of users in real-time.
[017] Another aspect of the present disclosure relates to a system for conducting interviews with real-time scoring using Artificial Intelligence (AI) and reducing carbon emissions. The system includes a processor and a memory. The memory operatively coupled with the processor, where the memory includes one or more instructions which, when executed, cause the processor to receive profile data of each of a plurality of applicants and select an applicant from the plurality of applicants based on the received profile data. Further, the processors are to determine identity information associated with the applicant based on the profile data and a token provided to the applicant, where the identity information comprises an image frame of the applicant, documents associated with the applicant, and biometric data of the applicant and validate the identity information and the profile data associated with the applicant. Further, upon validation, the processors are to initiate an interview through a wireless medium to establish a one-to-one communication between an applicant device and the system without using intermediate systems, where the interview is conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device to the applicant and receive responses and answers with respect to the set of interview questions from the applicant device of the applicant during the interview. Further, the processors are to evaluate in real-time via an AI engine, one or more attributes associated with the responses and the answers received from the applicant by comparing the one or more attributes with preset answers corresponding to the set of interview questions and generate a score for each of the one or more attributes associated with the responses and the answers, and a report based on the generated score of the applicant. Further, the processors are to provide the report of the applicant to a plurality of users in real-time.

BRIEF DESCRIPTION OF THE DRAWINGS
[018] FIG. 1A illustrates an exemplary architecture of an example system that communicates with an applicant device, in accordance with an embodiment of the present disclosure.
[019] FIG. 1B illustrates a block diagram of the example system for conducting interviews with real-time scoring using Artificial Intelligence (AI) and reducing carbon emissions, in accordance with an embodiment of the present disclosure.
[020] FIG. 2 illustrates a flow chart of an example method for conducting interviews with real-time scoring using AI and reducing carbon emissions, in accordance with an embodiment of the present disclosure.
[021] FIG. 3 illustrates a block diagram of an example computer system in which or with which embodiments of the present disclosure may be implemented.

DETAILED DESCRIPTION
[022] The present disclosure provides a technology designed to assist employers in conducting interviews and evaluating candidates for specific job requirements. A proposed system may utilize customizable interview questions tailored to job roles, paired with preset answers to streamline the evaluation process. Further, the interview sessions may be conducted by an Artificial Intelligence (AI) technique capable of hosting interviews in various formats and types, including one-on-one video call-style interactions. The AI-based platform operates globally, offering uninterrupted availability at all times, ensuring accessibility across different time zones and regions.
[023] The AI technique automates tasks over the internet, effectively handling repetitive functions, responding to queries, and interacting with users through text or voice. Additionally, the proposed system does not rely on external internet sources for evaluation. Instead, the proposed system functions within a closed framework, offering secure, efficient, and reliable performance without external data dependencies.
[024] Further, the proposed system begins by authenticating an applicant to verify identity and eligibility. In some embodiments, a snapshot of a current photograph of the applicant may be taken and used as part of a proctoring mechanism within the validity period of the interview. To ensure a secure and cheat-proof interview environment, the proposed system may integrate advanced technologies such as computer vision, object detection, movement detection, face detection, and speech detection. The technologies are embedded within a framework that monitors the interview environment for any suspicious activity or malpractice, ensuring integrity throughout the process. Further, the present disclosure enhances the hiring process by offering scalable, efficient, and customizable solutions and also ensures secure, fair, and unbiased evaluation of applicants in real-time.
[025] Additionally, the proposed system is configured to generate detailed reports in real time as soon as interview answers are submitted. The reports are comprehensive, featuring a scorecard that evaluates candidates based on various criteria such as, but not limited to, format, question type, and specific skills. The reports provide a nuanced analysis of communication skills, encompassing verbal, non-verbal, and written attributes, including style, tone, pace, and emotion, among other like attributes. This ensures that the candidate’s capabilities are presented as comprehensively as in a traditional video call or in-person interview.
[026] The responses of a candidate (or, the applicant) are transcribed and scored using advanced algorithms, while images and audio clips of the applicant are analyzed to generate a holistic and in-depth assessment. The underlying system leverages cutting-edge technologies such as computational linguistics, text analysis, and deep learning techniques. The integration of the technologies is further enhanced by utilizing tools and open-source AI solutions, enabling accurate and efficient evaluation. Furthermore, the present disclosure focuses on minimizing carbon emissions. The efficient AI application used herein achieves real-time evaluation with a substantially lower carbon footprint, offering a sustainable solution that aligns with global environmental goals.
[027] Accordingly, embodiments explained herein relate to the field of automated interview systems. In particular, the present disclosure relates to a system and a method for conducting interviews with real-time scoring using AI, thereby enhancing efficiency, improving accuracy, and reducing carbon emissions by optimizing data transfer, processing, and resource utilization.
[028] Various embodiments with respect to the present disclosure will be explained in detail with reference to FIGs. 1A-3.
[029] FIG. 1A illustrates an exemplary architecture 100A of an example system 102A that communicates with an applicant device 102C, in accordance with an embodiment of the present disclosure.
[030] Referring to FIG. 1A, the system 102A is designed to conduct interviews with real-time scoring by leveraging AI in a manner that significantly reduces carbon emissions. The reduction in carbon footprint is achieved by enabling direct communication between the system 102A and the applicant device 102C via a wireless medium 102B. This direct connection may eliminate the need for intermediate systems or servers that may consume additional energy for processing and data transmission, thereby reducing the overall energy requirements of the interview process. In exemplary embodiments, the applicant device may be, but not limited to computer systems, laptops, mobile phones or any other electronic devices. In exemplary embodiments, the wireless medium 102B may include, but not limited to technologies such as Wireless Fidelity (Wi-Fi), 4th Generation (4G) / 5th Generation (5G) cellular networks, Internet of Things (IoT) or other wireless communication protocols enabling data exchange without intermediate systems.
[031] Further, the system 102A may initiate the interview session, without an invigilator, through the wireless medium 102B, creating a seamless one-to-one communication link with the applicant device 102C. By avoiding reliance on third-party platforms or extensive server infrastructures for routing and processing the communication, the system 102A may minimize the carbon-intensive data transfer and redundant computational processes typically associated with online interviews conducted using conventional video conferencing tools.
[032] Furthermore, the AI-powered system 102A may intelligently manage data usage during the interview. Instead of streaming continuous high-bandwidth video feeds, the system 102A may employ optimized data exchange methods, such as transmitting compressed data packets or utilizing avatars and voice simulations, which emulate the experience of a real-time video interview without the associated high energy costs, thereby reducing the volume of data transmitted over the network, further contributing to lower energy consumption and carbon emissions. Additionally, the absence of the intermediate systems may ensure reduced latency and faster response times during the interview process. The efficiency not only enhances the user experience but also aligns with environmentally sustainable practices by eliminating unnecessary duplication of computational efforts across multiple platforms. The design, therefore, supports an eco-friendly method for conducting interviews while maintaining high reliability and accuracy in the assessment of applicants.
[033] FIG. 1B illustrates a block diagram 100B of an example system 102A for conducting interviews with real-time scoring using AI and reducing carbon emissions, in accordance with an embodiment of the present disclosure.
[034] Referring to FIG. 1B, the system 102A may include processor(s) 104, a memory 106, and an interface(s) 108. The processor(s) 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the processor(s) 104 may be configured to fetch and execute computer-readable instructions stored in the memory 106. The memory 106 may store one or more computer-readable instructions or routines, which may be fetched and executed the operations. The memory 106 may include any non-transitory storage device including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.
[035] The interface(s) 108 may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 108 may facilitate communication of the system 102A with various devices coupled to it. The interface(s) 108 may also provide a communication pathway for one or more components of the system 102A. Examples of such components may include, but are not limited to, processing engine(s) 110 and a database 112. The database 112 may include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 110.
[036] In an embodiment, the processing engine(s) 110 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 110. In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) 110 may be processor-executable instructions stored on a non-transitory machine-readable storage medium, and the hardware for the processor 104 may comprise a processing resource, to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 110. In such examples, the system 102A may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system 102A and the processing resource. In other examples, the processing engine(s) 110 may be implemented by an electronic circuitry. The processing engine(s) 110 may include a reception module 114, a selection module 116, an identity information module 118, a validation module 120, an initiation module 122, an evaluation module 124, a generation module 126, and other module(s) 128. The other module(s) 128 may implement functionalities that supplement applications/functions performed by the processing engine(s) 110. In exemplary embodiments, the other module(s) 128 may include a token generation module, a questions reception module, a presentation module, an event determination module, and the like. In an embodiment, each of the modules in the processing engine(s) 110 may be configured with an AI model. In an embodiment, the processing engine(s) 110 may be an AI engine.
[037] For conducting interviews with real-time scoring using AI, the reception module 114 may receive profile data of each of a plurality of applicants during a registration of each of the plurality of applicants at a webpage or a mobile application configured with the system 102A. In exemplary embodiments, the profile data may include, but not limited to, a resume, mark sheets, and the like.
[038] Once the profile data is received from each applicant, the selection module 116 may identify keywords associated with the profile data of the applicants and scan the profile data based on the keywords for selecting an applicant. For example, the system 102A may include multiple stages designed to streamline the online talent acquisition process, ensuring an efficient and secure method for candidate/applicant evaluation. Initially, a candidate screener may utilize Natural Language Processing (NLP) and search techniques to identify suitable candidates for interviews based on specific job requirements, enhancing the accuracy and speed of selecting potential candidates, ensuring only the most qualified applicants are considered for the interview process. In exemplary embodiments, the keywords may include be identified based on terms relevant to the job requirements to perform the selection process. For examples of such keywords include technical skills like “Python programming,” “Machine Learning,” or “Cloud Computing,” and soft skills such as “Team player,” “Leadership,” or “Problem-solving.” Additionally, certifications like “Amazon Web Services (AWS) Certified” or “Project Management Professional (PMP) Certification,” job-specific terms such as “User Interface/User Experience (UI/UX) Design” or “Financial Modelling,” and educational qualifications like “Bachelor's Degree in Computer Science” or “Master of Business Administration (MBA)” are often used. Keywords may also include experience-related phrases like “5+ years of experience” or “Cross-functional team management”.
[039] Once an applicant is selected, the token generation module (e.g., 128) may generate a token for the selected applicant and provide the generated token to the applicant. In an embodiment, the generated token may be stored in the database 112. In an embodiment, the token generation module 128 may compare the token (i.e., provided by the applicant) with token information pre-stored in the database 112 and authenticate the applicant based on the comparison. Once the applicant is authenticated, the token generation module 128 may determine whether the applicant accesses the interview within a predefined time period. If the applicant accesses the interview within the predefined time period, the identity information module 118 may determine identity information associated with the applicant based on the profile data and the token provided to the applicant. In an embodiment, the identity information may include, but not limited to, an image frame of the applicant, documents (e.g., the mark sheets, an identity proof, and the like) associated with the applicant, and biometric data (e.g., an image of the applicant, and the like) of the applicant.
[040] Further, the validation module 120 may compare the identity information and the profile data, and validate the identity information based on the comparison. Further, the initiation module 122 may initiate the interview through the wireless medium (e.g., 102B) to establish a one-to-one communication between the applicant device 102C associated with the applicant and the system 102A without using intermediate systems. In an embodiment, the interview may be conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device 102C to the applicant. For example, the AI-powered video assessment process may begin with candidate authentication, employing the token to confirm the identity of the candidate and validate the interview session. Following token verification, Identity (ID) authentication (e.g., the identity information) is performed, utilizing current biometric details such as a photograph and/or voice for proctoring, ensuring a secure and verified environment for the interview.
[041] In an embodiment, for displaying the set of interview questions, the questions reception module may receive a plurality of interview questions from a plurality of users (e.g., employers) associated with a plurality of organizations and automatically select the set of interview questions from the plurality of interview questions based on the profile data of the applicant. In some embodiments, the set of interview questions may be selected and presented to the candidate using a technique chosen by the employer. In exemplary embodiments, the set of interview questions may be generated using generative AI or provided by a human expert. The implementation of deep learning technologies and required logic is essential to ensure the accuracy and relevance of the questions posed.
[042] Further, the presentation module may present the set of interview questions to the applicant when the time duration of the interview is started based on the selection. For example, a preset list of questions tailored to the job role having predefined answers is used throughout the interview process.
[043] Once the time duration of the interview is started, the evaluation module 124 may receive responses and answers with respect to the set of interview questions from the applicant device 102C of the applicant. Once the responses and the answers are received, the evaluation module 124 may determine attributes associated with the responses and the answers. Further, the evaluation module 124 may evaluate the attributes by comparing the attributes with preset answers corresponding to the set of interview questions in real-time. In an embodiment, the attributes may include, but not limited to, evaluated data associated with the responses and the answers; written, verbal, and non-verbal nuances of the applicant; psychological indicators of the applicant; behavioural indicators of the applicant, and the like. In an embodiment, the response and the answers may be received in any one of, but not limited to, an image format, a text format, an audio format, a video format, or any combination thereof. Once the attributes are evaluated, the generation module 126 may generate a score for each of the attributes associated with the responses and the answers, and a report based on the generated score of the applicant. Further, the generation module 126 may provide the report of the applicant to the plurality of users in real-time.
[044] In exemplary embodiments, upon completion of all questions, the interview session is closed, and the responses are submitted to an application server for processing. A scoring model (e.g., the generation module 126) is activated, incorporating computational linguistics, text analysis, voice analysis, and image analysis. The scoring model includes a set of techniques designed to evaluate various criteria, as specified by the employer, including correctness of answers, content quality, tone, emotion, style, and speed across verbal, non-verbal, and written communication streams. Text analysis involves meaning matching and logical processes, utilizing open-source AI models to assess the candidate’s understanding rather than relying on rote memorization. Additionally, programming, problem-solving, and other question types may be evaluated through the scoring model, typically resulting in a numerical score or percentage, which can be further analysed according to the employer’s requirements.
[045] In exemplary embodiments, a final score and communication analysis is compiled into a real-time report accessible to the candidate, recruiter, trainee, or employer. The report may provide a comprehensive assessment of the performance of the candidate in terms of knowledge, competency, delivery, habits, and working style. The evaluation of verbal, non-verbal, and written communication skills provides insights into the overall communication abilities and personality of the candidate, offering a well-rounded profile of the applicant. This eliminates the need for the employer to invest significant time or manpower in conducting or evaluating the interview.
[046] During the interview, the event determination module may continuously monitor the applicant in real-time using, for example, sensors associated with the applicant device 102C during the interview. In an embodiment, the sensors in the applicant device 102C may include, but not limited to, a camera, a microphone, and the like. Further, the event determination module may detect whether an occurrence of events associated with the applicant exceeds a predetermined range or not. If the occurrence of events exceeds the predetermined range, the event determination module may provide a warning signal on the interface of the applicant device 102C to the applicant. Further, the event determination module may determine whether a count of the warning signal exceeds a predefined threshold or not. If the count of the warning signal exceeds the predefined threshold, the event determination module may terminate the interview for the applicant. In an embodiment, the events may include, but not limited to, looking off-screen, rapid eye movements, a localization of one or more electronic devices around the applicants, background sounds, background voices, one or more subject activities around the applicants, a movement of a cursor in a user interface associated with the system, an opening and closing of tabs or windows in the user interface, a behaviour of the applicants, malpractices, and status of the identity information.
[047] In exemplary embodiments, throughout the interview, a proctoring technique may be configured in the event determination module that monitors any malpractice, leveraging computer vision and various utilities to detect objects, facial movements, screen changes, cursor movements, faces, and voices. Multiple checks are implemented to ensure near-100% proctoring accuracy. If any malpractice is detected, a warning signal is issued, and the interview session is terminated. The system 102A may integrate the deep learning technologies and standard human behaviour logics, ensuring comprehensive proctoring that maintains the integrity of the interview process.
[048] Accordingly, as discussed herein, the interview process may proceed only once the candidate has been authenticated using the token, ID card, current photograph, and voice, ensuring continuous identification throughout the session. The interview typically progresses with questions presented in text format, with the expected answer format specified. Further, the responses may be recorded as text, audio, or images, with one-on-one video call-based interviews being recorded and transcribed for analysis. The system 102A may record spoken responses, ensuring an accurate transcription of the interview.
[049] Therefore, the present disclosure provides the AI-driven interviewing system 102A designed to autonomously manage the entire interview process. By employing AI, the system 102A ensures real-time evaluation of candidates, eliminating human biases and providing consistent, objective assessments. Further, the present disclosure streamlines the interviewing process, offering precision and fairness that traditional methods often lack.
[050] A significant feature of the present disclosure delivers highly customizable interview experiences. The set of interview questions can be randomized or tailored to align with specific job requisitions, with predefined answers already integrated into the system 102A. Leveraging global knowledge, the system 102A may generate relevant questions, ensuring each interview remains unique and reflective of current industry standards.
[051] Additionally, the present disclosure prioritizes environmental sustainability by minimizing carbon emissions associated with data storage, processing, and transfer. Further, the present disclosure is highly scalable, eco-friendly, and particularly suited for remote or online setups utilized by experts worldwide. In the rapidly expanding domains of talent acquisition, encompassing hiring, training, and upskilling, the system 102A represents a ground breaking approach. Automated interviewing with a reduced carbon footprint aligns with global sustainability goals, addressing the growing demand for efficient, environmentally conscious hiring processes while fostering scalability and flexibility.
[052] By reducing reliance on human resources, the system 102A addresses challenges like absenteeism, resource shortages, and attrition, thereby creating a seamless process flow. Additionally, the responses and the answers collected through interviews can be effectively leveraged to drive organizational growth, personal development, and process maturity. The present disclosure not only reduces operational costs but also maximizes the value derived from data, ensuring that organizations remain competitive and adaptive in a dynamic market landscape. Additionally, the present disclosure redefines talent acquisition, integrating advanced AI capabilities with sustainability and cost efficiency to meet the evolving needs of modern organizations.
[053] Additionally, the employers (e.g., the plurality of users) may fully customize interview questions using personal expertise or integrate globally available knowledge from online resources. The system 102A supports tailoring fixed questions and answers to align with specific skills or job roles, ensuring efficiency, consistency, and relevance. The present disclosure further emphasizes creating a secure and cheat-proof interview environment. Risks such as candidates leaving the screen, using other browsers, referring to notes, or employing proxies are mitigated through advanced monitoring techniques.
[054] Additionally, the simulation of a one-on-one video interview experience eliminates the need for traditional video calls or Web Real-Time Communication (WebRTC)-based communication. The AI technique conducts real-time analysis, conserving resources associated with video calls, including data storage, transmission, and processing, achieving up to a 99% reduction in carbon emissions through optimized software design. Key contributing factors include the selection of energy-efficient network technologies, protocols, content delivery networks, resource management techniques, and energy-efficient data centres.
[055] By using AI techniques, the system 102A minimizes environmental impact. By relying on fixed question-and-answer subsets, there is no requirement for dynamic generation of answers, resembling the efficiency of an interviewer who already knows the answers or an examiner evaluating against a prepared answer sheet. The system 102A provides a highly customizable experience, featuring elements such as voice personalization, avatars, logos, and other branding options. Beyond hiring, the AI technology is adaptable for various applications, including interview practice, job training, campus recruitment, language learning, or vocational training, providing expert guidance on demand. It may be appreciated that the system 102A is also applicable to the gig economy, providing comprehensive reports on freelancers or short-term contract workers. The AI-powered technology ensures unbiased candidate (e.g., the applicant) screening, assessment, and selection, delivering consistent and accurate results devoid of the biases commonly associated with human interviewers. The system 102A represents a sustainable approach to modern recruitment and skill assessment processes.
[056] Therefore, the system 102A may be configured to reduce the carbon footprint by minimizing the amount of data transferred and processed over a client-server internet-like transaction, rather than relying on a one-to-one video call. Additionally, the system 102A may provide an experience similar to a video call with voice and an avatar of the interviewer, while ensuring a more energy-efficient process. The system 102A may be scalable and integrated into the recruitment process followed by typical talent acquisition teams. The system 102A provides methods for scheduling interviews with shortlisted candidates and facilitates further evaluation using the same system 102A but with different assessments. While human decision-making is supported by data, complete replacement of human judgment is avoided, acknowledging the inherent nature of the industry. The technology can be further scaled for use in educational institutions, training organizations, and for the automated generation of certifications, among other applications. The system inputs and devices required include Wi-Fi, microphone, headphones, webcam, keyboard, and operating systems, browsers, sensors, and other connected technologies. The system 102A works over the internet, utilizing cloud infrastructure with dedicated accounts for companies and individuals, ensuring secure, unshared access to data while enabling the monitoring, analysis, and deduction of related personnel and company performance as applicable.
[057] FIG. 2 illustrates a flow chart of an example method 200 for conducting interviews with real-time scoring using AI and reducing carbon emissions, in accordance with an embodiment of the present disclosure.
[058] Referring to FIG. 2, at 202, the method 200 may include receiving, by a system (e.g., 102A as represented in FIG. 1A or 1B), profile data of each of a plurality of applicants. At 204, the method 200 may include selecting, by the system 102A, an applicant from the plurality of applicants based on the received profile data. At 206, the method 200 may include determining, by the system 102A, identity information associated with the applicant based on the profile data and a token provided to the applicant, where the identity information may include, but not limited to, an image frame of the applicant, documents associated with the applicant, and biometric data of the applicant. At 208, the method 200 may include validating, by the system 102A, the identity information and the profile data associated with the applicant.
[059] At 210, upon validation, the method 200 may include initiating, by the system 102A, an interview through a wireless medium (e.g., 102B as represented in FIG. 1A) to establish a one-to-one communication between an applicant device (e.g., 102C as represented in FIG. 1A) and the system 102A without using intermediate systems, where the interview is conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device 102C to the applicant. At 212, the method 200 may include receiving, by the system 102A, responses and answers with respect to the set of interview questions from the applicant device 102C of the applicant during the interview. At 214, the method 200 may include evaluating, in real-time, by the system 102A via an AI engine (e.g., 110), one or more attributes associated with the responses and the answers received from the applicant by comparing the one or more attributes with preset answers corresponding to the set of interview questions. At 216, the method 200 may include generating, by the system 102A, a score for each of the one or more attributes associated with the responses and the answers, and a report based on the generated score of the applicant. At 218, the method 200 may include providing, by the system 102A, the report of the applicant to a plurality of users in real-time.
[060] FIG. 3 illustrates a block diagram of an example computer system 300 in which or with which embodiments of the present disclosure may be implemented. As shown in FIG. 3, the computer system 300 may include an external storage device 310, a bus 320, a main memory 330, a read only memory 340, a mass storage device 350, a communication port 360, and a processor 370. In an embodiment, the communication port 360 may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. In an embodiment, the memory 330 may be a Random-Access Memory (RAM). The read-only memory 340 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information. In an embodiment, the mass storage device 350 may be any current or future mass storage solution. In an embodiment, the bus 320 communicatively couples the processor(s) 370 with the other memory, storage, and communication blocks. The bus 320 may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB or the like. Other operator and administrative interfaces may be provided through network connections connected through the communication port 360. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 300 limit the scope of the present disclosure.

ADVANTAGES OF THE PRESENT DISCLOSURE
[061] The present disclosure enables direct communication between an applicant device and a system without relying on intermediate systems, reducing unnecessary energy consumption and carbon emissions associated with data routing and processing.
[062] The present disclosure utilizes Artificial Intelligence (AI)-powered real-time scoring, enhancing the efficiency and accuracy of applicant evaluation while minimizing resource use by automating key processes.
[063] The present disclosure enhances applicant evaluation by incorporating AI techniques that assess verbal, non-verbal, and written responses in real-time, providing comprehensive feedback while minimizing the reliance on human interviewers and environmental footprint.
[064] The present disclosure ensures a bias-free evaluation process during interviews by leveraging AI-driven techniques, enabling fair and objective assessments of candidates.
, Claims:1. A method (200) for conducting interviews with real-time scoring using Artificial Intelligence (AI) and reducing carbon emissions, comprising:
receiving (202), by a system (102), profile data of each of a plurality of applicants;
selecting (204), by the system (102), an applicant from the plurality of applicants based on the received profile data;
determining (206), by the system (102), identity information associated with the applicant based on the profile data and a token provided to the applicant, wherein the identity information comprises an image frame of the applicant, documents associated with the applicant, and biometric data of the applicant;
validating (208), by the system (102), the identity information and the profile data associated with the applicant;
upon validation, initiating (210), by the system (102), an interview through a wireless medium (102B) to establish a one-to-one communication between an applicant device (102C) and the system (102) without using intermediate systems, wherein the interview is conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device (102C) to the applicant;
receiving (212), by the system (102), responses and answers with respect to the set of interview questions from the applicant device (102C) of the applicant during the interview;
evaluating, in real-time (214), by the system (102) via an AI engine, one or more attributes associated with the responses and the answers received from the applicant by comparing the one or more attributes with preset answers corresponding to the set of interview questions;
generating (216), by the system (102), a score for each of the one or more attributes associated with the responses and the answers, and a report based on the generated score of the applicant; and
providing (218), by the system (102), the report of the applicant to a plurality of users in real-time.

2. The method (200) as claimed in claim 1, wherein the one or more attributes comprise any one or a combination of: evaluated data associated with the responses and the answers; written, verbal, and non-verbal nuances of the applicant; psychological indicators of the applicant; and behavioural indicators of the applicant.

3. The method (200) as claimed in claim 1, wherein selecting (204), by the system (102), the applicant comprises:
identifying, by the system (102), keywords associated with the profile data of the applicant; and
scanning, by the system (102), the profile data based on the keywords for selecting the applicant.

4. The method (200) as claimed in claim 1, wherein in response to selecting (204), by the system (102), the applicant, the method (200) comprises:
generating, by the system (102), a token for the selected applicant;
providing, by the system (102), the generated token to the applicant;
storing, by the system (102), the generated token in a database (112) associated with the system (102);
comparing, by the system (102), the token with token information pre-stored in the database (112);
authenticating, by the system (102), the applicant based on the comparison of the token with the token information; and
determining, by the system (102), that the applicant accesses the interview within a predefined time period upon the authentication.

5. The method (200) as claimed in claim 1, comprising:
receiving, by the system (102), a plurality of interview questions from the plurality of users associated with a plurality of organizations;
automatically selecting, by the system (102), the set of interview questions from the plurality of interview questions based on the profile data of the applicant; and
displaying, by the system (102), the set of interview questions to the applicant on the interface when the time duration of the interview is started based on the selection.

6. The method (200) as claimed in claim 1, comprising:
continuously monitoring, by the system (102), the applicant in real-time during the interview using one or more sensors associated with the applicant device (102C);
detecting, by the system (102), that an occurrence of one or more events associated with the applicant exceeds a predetermined range;
providing, by the system (102), a warning signal on the interface to the applicant in response to the detection of the one or more events;
determining, by the system (102), that a count of the warning signal exceeds a predefined threshold; and
in response to determining that the count of the warning signal exceeds the predefined threshold, terminating, by the system (102), the interview for the applicant.

7. The method (200) as claimed in claim 6, wherein the one or more events comprise: looking off-screen, rapid eye movements, a localization of one or more electronic devices around the applicant, background sounds, background voices, one or more subject activities around the applicant, a movement of a cursor on a user interface associated with the system (102), an opening and/or closing of tabs or windows in the user interface, a behavior of the applicant, malpractices, and status of the identity information.

8. The method (200) as claimed in claim 1, comprising:
receiving, by the system (102), the response and the answers in any one of: an image format, a text format, an audio format, a video format, or any combination thereof.

9. A system (102) for conducting interviews with real-time scoring using Artificial Intelligence (AI) and reducing carbon emissions, comprising:
a processor (104); and
a memory (106) operatively coupled with the processor (104), wherein the memory (106) comprises one or more instructions which, when executed, cause the processor (104) to:
receive profile data of each of a plurality of applicants;
select an applicant from the plurality of applicants based on the received profile data;
determine identity information associated with the applicant based on the profile data and a token provided to the applicant, wherein the identity information comprises an image frame of the applicant, documents associated with the applicant, and biometric data of the applicant;
validate the identity information and the profile data associated with the applicant;
upon validation, initiate an interview through a wireless medium (102B) to establish a one-to-one communication between an applicant device (102C) and the system (102) without using intermediate systems, wherein the interview is conducted for a predefined time duration by displaying a set of interview questions on an interface of the applicant device (102C) to the applicant;
receive responses and answers with respect to the set of interview questions from the applicant device (102C) of the applicant during the interview;
evaluate in real-time via an AI engine, one or more attributes associated with the responses and the answers received from the applicant by comparing the one or more attributes with preset answers corresponding to the set of interview questions;
generate a score for each of the one or more attributes associated with the responses and the answers, and a report based on the generated score of the applicant; and
provide the report of the applicant to a plurality of users in real-time.